Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Conversation

vmoens
Copy link
Collaborator

@vmoens vmoens commented Nov 23, 2024

[ghstack-poisoned]
@pytorch-bot
Copy link

pytorch-bot bot commented Nov 23, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2598

Note: Links to docs will display an error until the docs builds have been completed.

❌ 13 New Failures, 5 Unrelated Failures

As of commit 0625dbc with merge base 152bc81 (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following job failed but was likely due to flakiness present on trunk:

BROKEN TRUNK - The following jobs failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Nov 23, 2024
[ghstack-poisoned]
@vmoens vmoens merged commit 0625dbc into gh/vmoens/45/base Nov 24, 2024
40 of 58 checks passed
vmoens pushed a commit that referenced this pull request Nov 24, 2024
ghstack-source-id: 64d5bd7
Pull Request resolved: #2598
@vmoens vmoens deleted the gh/vmoens/45/head branch November 24, 2024 08:16
@github-actions
Copy link

$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of CPU Benchmark Tests

Total Benchmarks: 149. Improved: $\large\color{#35bf28}15$. Worsened: $\large\color{#d91a1a}13$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4376s 0.4314s 2.3182 Ops/s 2.2154 Ops/s $\color{#35bf28}+4.64\%$
test_transformed 0.6180s 0.6047s 1.6538 Ops/s 1.6381 Ops/s $\color{#35bf28}+0.95\%$
test_serial 1.3705s 1.3500s 0.7407 Ops/s 0.7255 Ops/s $\color{#35bf28}+2.10\%$
test_parallel 1.3815s 1.2860s 0.7776 Ops/s 0.7554 Ops/s $\color{#35bf28}+2.94\%$
test_step_mdp_speed[True-True-True-True-True] 0.2074ms 26.7636μs 37.3642 KOps/s 36.4698 KOps/s $\color{#35bf28}+2.45\%$
test_step_mdp_speed[True-True-True-True-False] 66.1340μs 15.6396μs 63.9404 KOps/s 62.2347 KOps/s $\color{#35bf28}+2.74\%$
test_step_mdp_speed[True-True-True-False-True] 43.7120μs 15.2642μs 65.5129 KOps/s 63.9051 KOps/s $\color{#35bf28}+2.52\%$
test_step_mdp_speed[True-True-True-False-False] 40.7560μs 8.8297μs 113.2542 KOps/s 109.1680 KOps/s $\color{#35bf28}+3.74\%$
test_step_mdp_speed[True-True-False-True-True] 66.5040μs 28.7556μs 34.7759 KOps/s 34.1266 KOps/s $\color{#35bf28}+1.90\%$
test_step_mdp_speed[True-True-False-True-False] 68.7280μs 17.2790μs 57.8738 KOps/s 57.1720 KOps/s $\color{#35bf28}+1.23\%$
test_step_mdp_speed[True-True-False-False-True] 47.7890μs 17.0169μs 58.7651 KOps/s 58.4074 KOps/s $\color{#35bf28}+0.61\%$
test_step_mdp_speed[True-True-False-False-False] 57.3170μs 10.6048μs 94.2967 KOps/s 92.2809 KOps/s $\color{#35bf28}+2.18\%$
test_step_mdp_speed[True-False-True-True-True] 71.1030μs 30.4009μs 32.8938 KOps/s 31.8063 KOps/s $\color{#35bf28}+3.42\%$
test_step_mdp_speed[True-False-True-True-False] 0.6108ms 19.4283μs 51.4712 KOps/s 52.0374 KOps/s $\color{#d91a1a}-1.09\%$
test_step_mdp_speed[True-False-True-False-True] 62.4970μs 16.9411μs 59.0281 KOps/s 58.1800 KOps/s $\color{#35bf28}+1.46\%$
test_step_mdp_speed[True-False-True-False-False] 37.1490μs 10.4988μs 95.2490 KOps/s 92.9410 KOps/s $\color{#35bf28}+2.48\%$
test_step_mdp_speed[True-False-False-True-True] 67.2960μs 31.9590μs 31.2901 KOps/s 31.2258 KOps/s $\color{#35bf28}+0.21\%$
test_step_mdp_speed[True-False-False-True-False] 66.5110μs 20.8721μs 47.9108 KOps/s 48.0507 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[True-False-False-False-True] 74.0580μs 18.5365μs 53.9476 KOps/s 53.3085 KOps/s $\color{#35bf28}+1.20\%$
test_step_mdp_speed[True-False-False-False-False] 38.8430μs 12.3391μs 81.0431 KOps/s 81.1847 KOps/s $\color{#d91a1a}-0.17\%$
test_step_mdp_speed[False-True-True-True-True] 99.6360μs 29.9369μs 33.4036 KOps/s 32.4727 KOps/s $\color{#35bf28}+2.87\%$
test_step_mdp_speed[False-True-True-True-False] 53.8410μs 19.0130μs 52.5956 KOps/s 51.8671 KOps/s $\color{#35bf28}+1.40\%$
test_step_mdp_speed[False-True-True-False-True] 56.9460μs 19.3075μs 51.7932 KOps/s 51.1933 KOps/s $\color{#35bf28}+1.17\%$
test_step_mdp_speed[False-True-True-False-False] 40.7460μs 11.7540μs 85.0772 KOps/s 82.5564 KOps/s $\color{#35bf28}+3.05\%$
test_step_mdp_speed[False-True-False-True-True] 86.2410μs 31.6128μs 31.6328 KOps/s 30.8512 KOps/s $\color{#35bf28}+2.53\%$
test_step_mdp_speed[False-True-False-True-False] 73.2900μs 20.3096μs 49.2379 KOps/s 47.9437 KOps/s $\color{#35bf28}+2.70\%$
test_step_mdp_speed[False-True-False-False-True] 3.0315ms 20.9797μs 47.6651 KOps/s 46.4276 KOps/s $\color{#35bf28}+2.67\%$
test_step_mdp_speed[False-True-False-False-False] 54.3520μs 13.3617μs 74.8407 KOps/s 72.1067 KOps/s $\color{#35bf28}+3.79\%$
test_step_mdp_speed[False-False-True-True-True] 76.7230μs 33.8270μs 29.5622 KOps/s 29.0924 KOps/s $\color{#35bf28}+1.61\%$
test_step_mdp_speed[False-False-True-True-False] 67.6360μs 22.1291μs 45.1894 KOps/s 44.4422 KOps/s $\color{#35bf28}+1.68\%$
test_step_mdp_speed[False-False-True-False-True] 87.6530μs 20.9342μs 47.7688 KOps/s 45.7829 KOps/s $\color{#35bf28}+4.34\%$
test_step_mdp_speed[False-False-True-False-False] 0.7565ms 13.2363μs 75.5496 KOps/s 72.2696 KOps/s $\color{#35bf28}+4.54\%$
test_step_mdp_speed[False-False-False-True-True] 90.0550μs 34.4950μs 28.9897 KOps/s 28.5860 KOps/s $\color{#35bf28}+1.41\%$
test_step_mdp_speed[False-False-False-True-False] 54.0510μs 23.5678μs 42.4308 KOps/s 42.7487 KOps/s $\color{#d91a1a}-0.74\%$
test_step_mdp_speed[False-False-False-False-True] 77.2640μs 22.0351μs 45.3822 KOps/s 44.9732 KOps/s $\color{#35bf28}+0.91\%$
test_step_mdp_speed[False-False-False-False-False] 46.3460μs 14.7891μs 67.6174 KOps/s 66.2514 KOps/s $\color{#35bf28}+2.06\%$
test_values[generalized_advantage_estimate-True-True] 12.5012ms 9.6920ms 103.1775 Ops/s 101.7846 Ops/s $\color{#35bf28}+1.37\%$
test_values[vec_generalized_advantage_estimate-True-True] 38.8598ms 36.0630ms 27.7292 Ops/s 30.0418 Ops/s $\textbf{\color{#d91a1a}-7.70\%}$
test_values[td0_return_estimate-False-False] 0.2371ms 0.1763ms 5.6734 KOps/s 5.4176 KOps/s $\color{#35bf28}+4.72\%$
test_values[td1_return_estimate-False-False] 27.2792ms 24.3513ms 41.0656 Ops/s 40.0124 Ops/s $\color{#35bf28}+2.63\%$
test_values[vec_td1_return_estimate-False-False] 43.1735ms 36.2772ms 27.5655 Ops/s 29.9035 Ops/s $\textbf{\color{#d91a1a}-7.82\%}$
test_values[td_lambda_return_estimate-True-False] 44.1314ms 34.4127ms 29.0590 Ops/s 28.0069 Ops/s $\color{#35bf28}+3.76\%$
test_values[vec_td_lambda_return_estimate-True-False] 37.4442ms 35.8818ms 27.8693 Ops/s 30.0419 Ops/s $\textbf{\color{#d91a1a}-7.23\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.6541ms 8.4471ms 118.3836 Ops/s 114.1976 Ops/s $\color{#35bf28}+3.67\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2875ms 1.9132ms 522.6837 Ops/s 518.7638 Ops/s $\color{#35bf28}+0.76\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5492ms 0.3593ms 2.7835 KOps/s 2.7777 KOps/s $\color{#35bf28}+0.21\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 46.2973ms 41.9843ms 23.8184 Ops/s 25.7731 Ops/s $\textbf{\color{#d91a1a}-7.58\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.0905ms 3.0347ms 329.5179 Ops/s 328.0015 Ops/s $\color{#35bf28}+0.46\%$
test_dqn_speed[False-None] 6.6075ms 1.3156ms 760.1265 Ops/s 744.9799 Ops/s $\color{#35bf28}+2.03\%$
test_dqn_speed[False-backward] 2.5989ms 1.8450ms 542.0182 Ops/s 545.8382 Ops/s $\color{#d91a1a}-0.70\%$
test_dqn_speed[True-None] 0.6296ms 0.4579ms 2.1839 KOps/s 2.0747 KOps/s $\textbf{\color{#35bf28}+5.27\%}$
test_dqn_speed[True-backward] 1.1691ms 0.9357ms 1.0687 KOps/s 1.0972 KOps/s $\color{#d91a1a}-2.60\%$
test_dqn_speed[reduce-overhead-None] 0.7811ms 0.4557ms 2.1945 KOps/s 2.1387 KOps/s $\color{#35bf28}+2.61\%$
test_dqn_speed[reduce-overhead-backward] 0.9568ms 0.8773ms 1.1398 KOps/s 1.0435 KOps/s $\textbf{\color{#35bf28}+9.23\%}$
test_ddpg_speed[False-None] 0.1851s 3.3072ms 302.3707 Ops/s 354.3563 Ops/s $\textbf{\color{#d91a1a}-14.67\%}$
test_ddpg_speed[False-backward] 4.0195ms 3.8707ms 258.3480 Ops/s 254.1747 Ops/s $\color{#35bf28}+1.64\%$
test_ddpg_speed[True-None] 2.1861ms 1.0162ms 984.0438 Ops/s 996.4218 Ops/s $\color{#d91a1a}-1.24\%$
test_ddpg_speed[True-backward] 1.9661ms 1.8861ms 530.1816 Ops/s 523.1617 Ops/s $\color{#35bf28}+1.34\%$
test_ddpg_speed[reduce-overhead-None] 1.7127ms 1.0052ms 994.8548 Ops/s 981.2097 Ops/s $\color{#35bf28}+1.39\%$
test_ddpg_speed[reduce-overhead-backward] 1.9583ms 1.8835ms 530.9359 Ops/s 522.7825 Ops/s $\color{#35bf28}+1.56\%$
test_sac_speed[False-None] 9.1592ms 7.6681ms 130.4101 Ops/s 128.0946 Ops/s $\color{#35bf28}+1.81\%$
test_sac_speed[False-backward] 0.2041s 14.2416ms 70.2167 Ops/s 94.4862 Ops/s $\textbf{\color{#d91a1a}-25.69\%}$
test_sac_speed[True-None] 2.1820ms 1.8588ms 537.9939 Ops/s 530.5663 Ops/s $\color{#35bf28}+1.40\%$
test_sac_speed[True-backward] 3.6885ms 3.5616ms 280.7763 Ops/s 278.1791 Ops/s $\color{#35bf28}+0.93\%$
test_sac_speed[reduce-overhead-None] 5.5102ms 1.9411ms 515.1739 Ops/s 512.9304 Ops/s $\color{#35bf28}+0.44\%$
test_sac_speed[reduce-overhead-backward] 3.6487ms 3.5692ms 280.1773 Ops/s 279.8416 Ops/s $\color{#35bf28}+0.12\%$
test_redq_speed[False-None] 13.8399ms 12.8041ms 78.1002 Ops/s 76.7193 Ops/s $\color{#35bf28}+1.80\%$
test_redq_speed[False-backward] 24.6847ms 22.5336ms 44.3781 Ops/s 44.0977 Ops/s $\color{#35bf28}+0.64\%$
test_redq_speed[True-None] 5.5145ms 4.8191ms 207.5060 Ops/s 196.2100 Ops/s $\textbf{\color{#35bf28}+5.76\%}$
test_redq_speed[True-backward] 23.9490ms 13.0149ms 76.8349 Ops/s 81.3825 Ops/s $\textbf{\color{#d91a1a}-5.59\%}$
test_redq_speed[reduce-overhead-None] 5.6721ms 4.6042ms 217.1919 Ops/s 187.9849 Ops/s $\textbf{\color{#35bf28}+15.54\%}$
test_redq_speed[reduce-overhead-backward] 24.2415ms 13.1682ms 75.9406 Ops/s 82.4016 Ops/s $\textbf{\color{#d91a1a}-7.84\%}$
test_redq_deprec_speed[False-None] 17.2589ms 13.3212ms 75.0683 Ops/s 77.5617 Ops/s $\color{#d91a1a}-3.21\%$
test_redq_deprec_speed[False-backward] 21.6007ms 18.8912ms 52.9346 Ops/s 53.7721 Ops/s $\color{#d91a1a}-1.56\%$
test_redq_deprec_speed[True-None] 10.2519ms 3.7885ms 263.9544 Ops/s 269.5155 Ops/s $\color{#d91a1a}-2.06\%$
test_redq_deprec_speed[True-backward] 8.9824ms 8.2230ms 121.6102 Ops/s 112.4376 Ops/s $\textbf{\color{#35bf28}+8.16\%}$
test_redq_deprec_speed[reduce-overhead-None] 8.7811ms 3.9423ms 253.6611 Ops/s 258.6638 Ops/s $\color{#d91a1a}-1.93\%$
test_redq_deprec_speed[reduce-overhead-backward] 12.6102ms 9.2866ms 107.6823 Ops/s 117.9537 Ops/s $\textbf{\color{#d91a1a}-8.71\%}$
test_td3_speed[False-None] 10.2857ms 7.6193ms 131.2463 Ops/s 123.3687 Ops/s $\textbf{\color{#35bf28}+6.39\%}$
test_td3_speed[False-backward] 12.1386ms 10.0738ms 99.2674 Ops/s 89.6793 Ops/s $\textbf{\color{#35bf28}+10.69\%}$
test_td3_speed[True-None] 3.8439ms 1.8257ms 547.7434 Ops/s 543.6651 Ops/s $\color{#35bf28}+0.75\%$
test_td3_speed[True-backward] 3.7880ms 3.4588ms 289.1201 Ops/s 291.0023 Ops/s $\color{#d91a1a}-0.65\%$
test_td3_speed[reduce-overhead-None] 1.8341ms 1.7388ms 575.1152 Ops/s 551.7589 Ops/s $\color{#35bf28}+4.23\%$
test_td3_speed[reduce-overhead-backward] 9.6304ms 4.1323ms 241.9968 Ops/s 294.1726 Ops/s $\textbf{\color{#d91a1a}-17.74\%}$
test_cql_speed[False-None] 37.5619ms 35.3564ms 28.2834 Ops/s 27.0224 Ops/s $\color{#35bf28}+4.67\%$
test_cql_speed[False-backward] 51.2487ms 46.1210ms 21.6821 Ops/s 20.9969 Ops/s $\color{#35bf28}+3.26\%$
test_cql_speed[True-None] 16.6271ms 15.6398ms 63.9395 Ops/s 61.8823 Ops/s $\color{#35bf28}+3.32\%$
test_cql_speed[True-backward] 23.8835ms 22.7894ms 43.8800 Ops/s 42.7700 Ops/s $\color{#35bf28}+2.60\%$
test_cql_speed[reduce-overhead-None] 23.5063ms 16.1032ms 62.0996 Ops/s 62.6131 Ops/s $\color{#d91a1a}-0.82\%$
test_cql_speed[reduce-overhead-backward] 24.1431ms 22.9203ms 43.6295 Ops/s 43.8734 Ops/s $\color{#d91a1a}-0.56\%$
test_a2c_speed[False-None] 8.8855ms 7.3796ms 135.5090 Ops/s 136.8698 Ops/s $\color{#d91a1a}-0.99\%$
test_a2c_speed[False-backward] 15.4469ms 14.5176ms 68.8819 Ops/s 69.5441 Ops/s $\color{#d91a1a}-0.95\%$
test_a2c_speed[True-None] 4.8991ms 4.2564ms 234.9421 Ops/s 233.0426 Ops/s $\color{#35bf28}+0.82\%$
test_a2c_speed[True-backward] 11.9319ms 11.0238ms 90.7128 Ops/s 90.0004 Ops/s $\color{#35bf28}+0.79\%$
test_a2c_speed[reduce-overhead-None] 8.2379ms 4.5941ms 217.6708 Ops/s 232.9145 Ops/s $\textbf{\color{#d91a1a}-6.54\%}$
test_a2c_speed[reduce-overhead-backward] 11.2043ms 10.9214ms 91.5637 Ops/s 91.5163 Ops/s $\color{#35bf28}+0.05\%$
test_ppo_speed[False-None] 8.9755ms 7.3475ms 136.1007 Ops/s 128.3590 Ops/s $\textbf{\color{#35bf28}+6.03\%}$
test_ppo_speed[False-backward] 18.4504ms 14.9699ms 66.8009 Ops/s 67.2694 Ops/s $\color{#d91a1a}-0.70\%$
test_ppo_speed[True-None] 6.2870ms 3.8153ms 262.0993 Ops/s 251.6988 Ops/s $\color{#35bf28}+4.13\%$
test_ppo_speed[True-backward] 12.0596ms 10.6073ms 94.2744 Ops/s 98.4769 Ops/s $\color{#d91a1a}-4.27\%$
test_ppo_speed[reduce-overhead-None] 5.3838ms 4.0427ms 247.3592 Ops/s 249.4800 Ops/s $\color{#d91a1a}-0.85\%$
test_ppo_speed[reduce-overhead-backward] 11.3360ms 10.1760ms 98.2708 Ops/s 92.5934 Ops/s $\textbf{\color{#35bf28}+6.13\%}$
test_reinforce_speed[False-None] 8.2035ms 6.7673ms 147.7684 Ops/s 149.6850 Ops/s $\color{#d91a1a}-1.28\%$
test_reinforce_speed[False-backward] 12.0396ms 10.4137ms 96.0275 Ops/s 99.7600 Ops/s $\color{#d91a1a}-3.74\%$
test_reinforce_speed[True-None] 3.3813ms 2.7675ms 361.3360 Ops/s 362.9305 Ops/s $\color{#d91a1a}-0.44\%$
test_reinforce_speed[True-backward] 9.5457ms 8.8688ms 112.7552 Ops/s 108.1068 Ops/s $\color{#35bf28}+4.30\%$
test_reinforce_speed[reduce-overhead-None] 7.1254ms 2.8092ms 355.9682 Ops/s 368.1044 Ops/s $\color{#d91a1a}-3.30\%$
test_reinforce_speed[reduce-overhead-backward] 9.3721ms 8.7814ms 113.8764 Ops/s 114.9464 Ops/s $\color{#d91a1a}-0.93\%$
test_iql_speed[False-None] 37.6560ms 32.5124ms 30.7575 Ops/s 30.5403 Ops/s $\color{#35bf28}+0.71\%$
test_iql_speed[False-backward] 48.7391ms 45.6170ms 21.9217 Ops/s 21.4201 Ops/s $\color{#35bf28}+2.34\%$
test_iql_speed[True-None] 15.0753ms 11.0260ms 90.6943 Ops/s 89.9237 Ops/s $\color{#35bf28}+0.86\%$
test_iql_speed[True-backward] 23.6817ms 21.9607ms 45.5358 Ops/s 44.5809 Ops/s $\color{#35bf28}+2.14\%$
test_iql_speed[reduce-overhead-None] 11.9078ms 11.0016ms 90.8958 Ops/s 90.6021 Ops/s $\color{#35bf28}+0.32\%$
test_iql_speed[reduce-overhead-backward] 22.9698ms 22.3122ms 44.8185 Ops/s 44.3818 Ops/s $\color{#35bf28}+0.98\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.6226ms 5.0546ms 197.8407 Ops/s 194.3223 Ops/s $\color{#35bf28}+1.81\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.1127ms 0.5183ms 1.9295 KOps/s 1.7691 KOps/s $\textbf{\color{#35bf28}+9.06\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7040ms 0.4942ms 2.0233 KOps/s 1.9591 KOps/s $\color{#35bf28}+3.27\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 8.4440ms 4.9366ms 202.5685 Ops/s 206.4184 Ops/s $\color{#d91a1a}-1.87\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0421ms 0.5076ms 1.9700 KOps/s 1.9753 KOps/s $\color{#d91a1a}-0.27\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7473ms 0.4819ms 2.0751 KOps/s 2.0442 KOps/s $\color{#35bf28}+1.51\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.8482ms 1.6218ms 616.6107 Ops/s 603.2486 Ops/s $\color{#35bf28}+2.22\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.7983ms 1.6053ms 622.9318 Ops/s 612.5852 Ops/s $\color{#35bf28}+1.69\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 9.1143ms 5.2144ms 191.7775 Ops/s 187.7210 Ops/s $\color{#35bf28}+2.16\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.4177ms 0.6437ms 1.5534 KOps/s 1.4756 KOps/s $\textbf{\color{#35bf28}+5.27\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.1876ms 0.6297ms 1.5880 KOps/s 1.5281 KOps/s $\color{#35bf28}+3.92\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.3856ms 4.7201ms 211.8584 Ops/s 197.4240 Ops/s $\textbf{\color{#35bf28}+7.31\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.6050ms 0.5215ms 1.9175 KOps/s 1.8286 KOps/s $\color{#35bf28}+4.86\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7958ms 0.4971ms 2.0117 KOps/s 1.9819 KOps/s $\color{#35bf28}+1.50\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.7094ms 4.7941ms 208.5913 Ops/s 201.4518 Ops/s $\color{#35bf28}+3.54\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6610ms 0.5007ms 1.9974 KOps/s 1.9425 KOps/s $\color{#35bf28}+2.82\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 7.9715ms 0.4947ms 2.0214 KOps/s 2.0783 KOps/s $\color{#d91a1a}-2.74\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.8703ms 4.9563ms 201.7631 Ops/s 198.8532 Ops/s $\color{#35bf28}+1.46\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.4629ms 0.6446ms 1.5513 KOps/s 1.4621 KOps/s $\textbf{\color{#35bf28}+6.10\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8650ms 0.6208ms 1.6109 KOps/s 1.5514 KOps/s $\color{#35bf28}+3.83\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.4272s 12.5135ms 79.9136 Ops/s 240.3223 Ops/s $\textbf{\color{#d91a1a}-66.75\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 6.5785ms 2.2439ms 445.6487 Ops/s 458.1116 Ops/s $\color{#d91a1a}-2.72\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 5.9433ms 1.3978ms 715.3869 Ops/s 626.7075 Ops/s $\textbf{\color{#35bf28}+14.15\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 5.6210ms 4.1389ms 241.6086 Ops/s 252.6102 Ops/s $\color{#d91a1a}-4.36\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 7.6619ms 2.3408ms 427.2026 Ops/s 430.2507 Ops/s $\color{#d91a1a}-0.71\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.0588ms 1.3868ms 721.0904 Ops/s 706.8097 Ops/s $\color{#35bf28}+2.02\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4329s 12.8330ms 77.9242 Ops/s 240.5121 Ops/s $\textbf{\color{#d91a1a}-67.60\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 10.4173ms 2.4316ms 411.2571 Ops/s 407.1035 Ops/s $\color{#35bf28}+1.02\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.3019ms 1.4870ms 672.4734 Ops/s 685.5533 Ops/s $\color{#d91a1a}-1.91\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.8965ms 11.1622ms 89.5884 Ops/s 87.0004 Ops/s $\color{#35bf28}+2.97\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 14.6677ms 14.3210ms 69.8276 Ops/s 68.3005 Ops/s $\color{#35bf28}+2.24\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.3909ms 19.7696ms 50.5828 Ops/s 46.6226 Ops/s $\textbf{\color{#35bf28}+8.49\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 15.1082ms 14.4874ms 69.0256 Ops/s 67.4601 Ops/s $\color{#35bf28}+2.32\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 20.2572ms 19.7043ms 50.7502 Ops/s 48.4578 Ops/s $\color{#35bf28}+4.73\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 16.9632ms 15.6709ms 63.8125 Ops/s 61.8211 Ops/s $\color{#35bf28}+3.22\%$

@github-actions
Copy link

$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of GPU Benchmark Tests

Total Benchmarks: 149. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}14$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7435s 0.7423s 1.3472 Ops/s 1.3581 Ops/s $\color{#d91a1a}-0.80\%$
test_transformed 0.9898s 0.9885s 1.0116 Ops/s 1.0246 Ops/s $\color{#d91a1a}-1.27\%$
test_serial 2.1431s 2.1377s 0.4678 Ops/s 0.4761 Ops/s $\color{#d91a1a}-1.74\%$
test_parallel 2.0314s 1.9696s 0.5077 Ops/s 0.5082 Ops/s $\color{#d91a1a}-0.09\%$
test_step_mdp_speed[True-True-True-True-True] 0.1887ms 36.0812μs 27.7153 KOps/s 28.6070 KOps/s $\color{#d91a1a}-3.12\%$
test_step_mdp_speed[True-True-True-True-False] 45.8110μs 21.0582μs 47.4874 KOps/s 49.8729 KOps/s $\color{#d91a1a}-4.78\%$
test_step_mdp_speed[True-True-True-False-True] 49.5110μs 20.1052μs 49.7384 KOps/s 51.7446 KOps/s $\color{#d91a1a}-3.88\%$
test_step_mdp_speed[True-True-True-False-False] 45.8310μs 11.5993μs 86.2121 KOps/s 88.3510 KOps/s $\color{#d91a1a}-2.42\%$
test_step_mdp_speed[True-True-False-True-True] 73.5120μs 38.5284μs 25.9549 KOps/s 26.5018 KOps/s $\color{#d91a1a}-2.06\%$
test_step_mdp_speed[True-True-False-True-False] 47.8910μs 22.4937μs 44.4569 KOps/s 45.5807 KOps/s $\color{#d91a1a}-2.47\%$
test_step_mdp_speed[True-True-False-False-True] 57.3910μs 22.0745μs 45.3012 KOps/s 46.7005 KOps/s $\color{#d91a1a}-3.00\%$
test_step_mdp_speed[True-True-False-False-False] 34.4010μs 13.5949μs 73.5569 KOps/s 74.7819 KOps/s $\color{#d91a1a}-1.64\%$
test_step_mdp_speed[True-False-True-True-True] 75.8410μs 40.2772μs 24.8279 KOps/s 25.2930 KOps/s $\color{#d91a1a}-1.84\%$
test_step_mdp_speed[True-False-True-True-False] 53.7310μs 24.5883μs 40.6697 KOps/s 42.7274 KOps/s $\color{#d91a1a}-4.82\%$
test_step_mdp_speed[True-False-True-False-True] 47.4100μs 22.3923μs 44.6582 KOps/s 47.2827 KOps/s $\textbf{\color{#d91a1a}-5.55\%}$
test_step_mdp_speed[True-False-True-False-False] 44.5710μs 13.5513μs 73.7936 KOps/s 74.2814 KOps/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[True-False-False-True-True] 0.5336ms 41.5562μs 24.0638 KOps/s 23.9904 KOps/s $\color{#35bf28}+0.31\%$
test_step_mdp_speed[True-False-False-True-False] 57.4510μs 26.6187μs 37.5675 KOps/s 37.9338 KOps/s $\color{#d91a1a}-0.97\%$
test_step_mdp_speed[True-False-False-False-True] 53.1800μs 24.3427μs 41.0801 KOps/s 42.1802 KOps/s $\color{#d91a1a}-2.61\%$
test_step_mdp_speed[True-False-False-False-False] 45.3810μs 15.7110μs 63.6497 KOps/s 65.4150 KOps/s $\color{#d91a1a}-2.70\%$
test_step_mdp_speed[False-True-True-True-True] 72.6010μs 40.2635μs 24.8364 KOps/s 24.8871 KOps/s $\color{#d91a1a}-0.20\%$
test_step_mdp_speed[False-True-True-True-False] 50.7410μs 24.7072μs 40.4740 KOps/s 40.6247 KOps/s $\color{#d91a1a}-0.37\%$
test_step_mdp_speed[False-True-True-False-True] 48.2410μs 25.7485μs 38.8372 KOps/s 38.8757 KOps/s $\color{#d91a1a}-0.10\%$
test_step_mdp_speed[False-True-True-False-False] 59.8710μs 15.2405μs 65.6147 KOps/s 65.4976 KOps/s $\color{#35bf28}+0.18\%$
test_step_mdp_speed[False-True-False-True-True] 71.8120μs 42.2322μs 23.6786 KOps/s 23.6315 KOps/s $\color{#35bf28}+0.20\%$
test_step_mdp_speed[False-True-False-True-False] 58.6110μs 26.7493μs 37.3841 KOps/s 38.0049 KOps/s $\color{#d91a1a}-1.63\%$
test_step_mdp_speed[False-True-False-False-True] 3.4117ms 28.0566μs 35.6422 KOps/s 36.4940 KOps/s $\color{#d91a1a}-2.33\%$
test_step_mdp_speed[False-True-False-False-False] 50.8510μs 17.4515μs 57.3016 KOps/s 58.6415 KOps/s $\color{#d91a1a}-2.28\%$
test_step_mdp_speed[False-False-True-True-True] 84.1620μs 44.6094μs 22.4168 KOps/s 22.6966 KOps/s $\color{#d91a1a}-1.23\%$
test_step_mdp_speed[False-False-True-True-False] 58.3210μs 28.6850μs 34.8615 KOps/s 35.3054 KOps/s $\color{#d91a1a}-1.26\%$
test_step_mdp_speed[False-False-True-False-True] 50.5610μs 27.4203μs 36.4694 KOps/s 37.5244 KOps/s $\color{#d91a1a}-2.81\%$
test_step_mdp_speed[False-False-True-False-False] 53.4410μs 17.1715μs 58.2360 KOps/s 59.0276 KOps/s $\color{#d91a1a}-1.34\%$
test_step_mdp_speed[False-False-False-True-True] 77.9120μs 46.9436μs 21.3022 KOps/s 22.3539 KOps/s $\color{#d91a1a}-4.71\%$
test_step_mdp_speed[False-False-False-True-False] 61.3820μs 30.6046μs 32.6748 KOps/s 33.7532 KOps/s $\color{#d91a1a}-3.20\%$
test_step_mdp_speed[False-False-False-False-True] 59.0210μs 28.9063μs 34.5945 KOps/s 34.6767 KOps/s $\color{#d91a1a}-0.24\%$
test_step_mdp_speed[False-False-False-False-False] 50.1810μs 19.0781μs 52.4162 KOps/s 53.8195 KOps/s $\color{#d91a1a}-2.61\%$
test_values[generalized_advantage_estimate-True-True] 25.3129ms 24.8937ms 40.1709 Ops/s 39.3713 Ops/s $\color{#35bf28}+2.03\%$
test_values[vec_generalized_advantage_estimate-True-True] 98.8845ms 2.8811ms 347.0949 Ops/s 317.6892 Ops/s $\textbf{\color{#35bf28}+9.26\%}$
test_values[td0_return_estimate-False-False] 0.1068ms 78.9172μs 12.6715 KOps/s 11.7991 KOps/s $\textbf{\color{#35bf28}+7.39\%}$
test_values[td1_return_estimate-False-False] 56.5339ms 55.7478ms 17.9379 Ops/s 17.9065 Ops/s $\color{#35bf28}+0.18\%$
test_values[vec_td1_return_estimate-False-False] 1.3148ms 1.0814ms 924.7333 Ops/s 918.1328 Ops/s $\color{#35bf28}+0.72\%$
test_values[td_lambda_return_estimate-True-False] 88.7493ms 88.0246ms 11.3605 Ops/s 11.3567 Ops/s $\color{#35bf28}+0.03\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3253ms 1.0837ms 922.7988 Ops/s 917.9280 Ops/s $\color{#35bf28}+0.53\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.1337ms 24.9327ms 40.1080 Ops/s 40.3580 Ops/s $\color{#d91a1a}-0.62\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0580ms 0.7623ms 1.3119 KOps/s 1.3177 KOps/s $\color{#d91a1a}-0.44\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7643ms 0.6717ms 1.4887 KOps/s 1.4444 KOps/s $\color{#35bf28}+3.06\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5310ms 1.4776ms 676.7846 Ops/s 675.3996 Ops/s $\color{#35bf28}+0.21\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7242ms 0.6872ms 1.4551 KOps/s 1.4557 KOps/s $\color{#d91a1a}-0.04\%$
test_dqn_speed[False-None] 7.2574ms 1.4470ms 691.0721 Ops/s 708.2331 Ops/s $\color{#d91a1a}-2.42\%$
test_dqn_speed[False-backward] 2.0917ms 2.0484ms 488.1892 Ops/s 493.5915 Ops/s $\color{#d91a1a}-1.09\%$
test_dqn_speed[True-None] 0.6614ms 0.5338ms 1.8732 KOps/s 1.7941 KOps/s $\color{#35bf28}+4.41\%$
test_dqn_speed[True-backward] 1.2605ms 1.1964ms 835.8372 Ops/s 907.9235 Ops/s $\textbf{\color{#d91a1a}-7.94\%}$
test_dqn_speed[reduce-overhead-None] 0.6197ms 0.5444ms 1.8370 KOps/s 1.8353 KOps/s $\color{#35bf28}+0.10\%$
test_dqn_speed[reduce-overhead-backward] 1.1239ms 1.0644ms 939.4616 Ops/s 1.0527 KOps/s $\textbf{\color{#d91a1a}-10.75\%}$
test_ddpg_speed[False-None] 3.0177ms 2.6969ms 370.7971 Ops/s 372.3685 Ops/s $\color{#d91a1a}-0.42\%$
test_ddpg_speed[False-backward] 4.5193ms 4.0921ms 244.3714 Ops/s 254.1152 Ops/s $\color{#d91a1a}-3.83\%$
test_ddpg_speed[True-None] 1.1489ms 1.0818ms 924.3529 Ops/s 929.7552 Ops/s $\color{#d91a1a}-0.58\%$
test_ddpg_speed[True-backward] 2.3940ms 2.3029ms 434.2385 Ops/s 461.9559 Ops/s $\textbf{\color{#d91a1a}-6.00\%}$
test_ddpg_speed[reduce-overhead-None] 1.1358ms 1.0917ms 915.9909 Ops/s 918.9174 Ops/s $\color{#d91a1a}-0.32\%$
test_ddpg_speed[reduce-overhead-backward] 1.8302ms 1.7623ms 567.4425 Ops/s 613.8915 Ops/s $\textbf{\color{#d91a1a}-7.57\%}$
test_sac_speed[False-None] 8.3219ms 7.7795ms 128.5438 Ops/s 129.0686 Ops/s $\color{#d91a1a}-0.41\%$
test_sac_speed[False-backward] 11.1888ms 10.7038ms 93.4248 Ops/s 93.3124 Ops/s $\color{#35bf28}+0.12\%$
test_sac_speed[True-None] 1.6100ms 1.5270ms 654.8662 Ops/s 655.8476 Ops/s $\color{#d91a1a}-0.15\%$
test_sac_speed[True-backward] 3.2699ms 3.1965ms 312.8437 Ops/s 311.8419 Ops/s $\color{#35bf28}+0.32\%$
test_sac_speed[reduce-overhead-None] 22.7875ms 12.5696ms 79.5570 Ops/s 78.5810 Ops/s $\color{#35bf28}+1.24\%$
test_sac_speed[reduce-overhead-backward] 1.5355ms 1.4783ms 676.4548 Ops/s 757.2794 Ops/s $\textbf{\color{#d91a1a}-10.67\%}$
test_redq_speed[False-None] 8.1237ms 7.2329ms 138.2563 Ops/s 135.3506 Ops/s $\color{#35bf28}+2.15\%$
test_redq_speed[False-backward] 12.2872ms 11.3519ms 88.0914 Ops/s 89.3716 Ops/s $\color{#d91a1a}-1.43\%$
test_redq_speed[True-None] 2.0356ms 1.9702ms 507.5632 Ops/s 508.6330 Ops/s $\color{#d91a1a}-0.21\%$
test_redq_speed[True-backward] 3.6948ms 3.5853ms 278.9144 Ops/s 277.9830 Ops/s $\color{#35bf28}+0.34\%$
test_redq_speed[reduce-overhead-None] 2.0491ms 1.9717ms 507.1868 Ops/s 509.6094 Ops/s $\color{#d91a1a}-0.48\%$
test_redq_speed[reduce-overhead-backward] 3.8673ms 3.7844ms 264.2455 Ops/s 276.9788 Ops/s $\color{#d91a1a}-4.60\%$
test_redq_deprec_speed[False-None] 9.2048ms 8.7304ms 114.5416 Ops/s 114.2565 Ops/s $\color{#35bf28}+0.25\%$
test_redq_deprec_speed[False-backward] 12.6352ms 11.9804ms 83.4695 Ops/s 84.6356 Ops/s $\color{#d91a1a}-1.38\%$
test_redq_deprec_speed[True-None] 2.4089ms 2.2919ms 436.3230 Ops/s 435.2779 Ops/s $\color{#35bf28}+0.24\%$
test_redq_deprec_speed[True-backward] 4.2305ms 4.1290ms 242.1865 Ops/s 253.7340 Ops/s $\color{#d91a1a}-4.55\%$
test_redq_deprec_speed[reduce-overhead-None] 2.5062ms 2.3326ms 428.6984 Ops/s 437.1684 Ops/s $\color{#d91a1a}-1.94\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.5206ms 4.1147ms 243.0292 Ops/s 241.7658 Ops/s $\color{#35bf28}+0.52\%$
test_td3_speed[False-None] 7.8647ms 7.6069ms 131.4594 Ops/s 133.6431 Ops/s $\color{#d91a1a}-1.63\%$
test_td3_speed[False-backward] 10.5809ms 10.1301ms 98.7157 Ops/s 99.1694 Ops/s $\color{#d91a1a}-0.46\%$
test_td3_speed[True-None] 1.6004ms 1.5595ms 641.2367 Ops/s 642.9770 Ops/s $\color{#d91a1a}-0.27\%$
test_td3_speed[True-backward] 3.3150ms 3.2378ms 308.8518 Ops/s 310.0659 Ops/s $\color{#d91a1a}-0.39\%$
test_td3_speed[reduce-overhead-None] 80.0729ms 25.6014ms 39.0604 Ops/s 38.4001 Ops/s $\color{#35bf28}+1.72\%$
test_td3_speed[reduce-overhead-backward] 1.5241ms 1.4423ms 693.3508 Ops/s 788.8217 Ops/s $\textbf{\color{#d91a1a}-12.10\%}$
test_cql_speed[False-None] 16.0881ms 15.6761ms 63.7912 Ops/s 64.2423 Ops/s $\color{#d91a1a}-0.70\%$
test_cql_speed[False-backward] 21.5213ms 21.0382ms 47.5327 Ops/s 48.2133 Ops/s $\color{#d91a1a}-1.41\%$
test_cql_speed[True-None] 3.0943ms 2.9232ms 342.0875 Ops/s 336.7654 Ops/s $\color{#35bf28}+1.58\%$
test_cql_speed[True-backward] 5.4575ms 5.0066ms 199.7370 Ops/s 191.9341 Ops/s $\color{#35bf28}+4.07\%$
test_cql_speed[reduce-overhead-None] 21.1639ms 12.9841ms 77.0172 Ops/s 76.8983 Ops/s $\color{#35bf28}+0.15\%$
test_cql_speed[reduce-overhead-backward] 1.5364ms 1.4681ms 681.1355 Ops/s 687.4564 Ops/s $\color{#d91a1a}-0.92\%$
test_a2c_speed[False-None] 3.2667ms 3.1003ms 322.5490 Ops/s 316.0110 Ops/s $\color{#35bf28}+2.07\%$
test_a2c_speed[False-backward] 6.8084ms 5.9715ms 167.4615 Ops/s 165.7586 Ops/s $\color{#35bf28}+1.03\%$
test_a2c_speed[True-None] 1.0467ms 0.9819ms 1.0184 KOps/s 1.0182 KOps/s $\color{#35bf28}+0.02\%$
test_a2c_speed[True-backward] 2.7951ms 2.6358ms 379.3872 Ops/s 387.2820 Ops/s $\color{#d91a1a}-2.04\%$
test_a2c_speed[reduce-overhead-None] 0.3824s 12.3901ms 80.7093 Ops/s 87.1776 Ops/s $\textbf{\color{#d91a1a}-7.42\%}$
test_a2c_speed[reduce-overhead-backward] 1.0301ms 0.9777ms 1.0228 KOps/s 1.0289 KOps/s $\color{#d91a1a}-0.59\%$
test_ppo_speed[False-None] 3.8161ms 3.5950ms 278.1603 Ops/s 281.4684 Ops/s $\color{#d91a1a}-1.18\%$
test_ppo_speed[False-backward] 7.0770ms 6.7084ms 149.0677 Ops/s 149.5990 Ops/s $\color{#d91a1a}-0.36\%$
test_ppo_speed[True-None] 1.0029ms 0.9296ms 1.0758 KOps/s 1.0696 KOps/s $\color{#35bf28}+0.57\%$
test_ppo_speed[True-backward] 2.7574ms 2.5855ms 386.7753 Ops/s 392.1019 Ops/s $\color{#d91a1a}-1.36\%$
test_ppo_speed[reduce-overhead-None] 0.5477ms 0.4859ms 2.0582 KOps/s 1.9182 KOps/s $\textbf{\color{#35bf28}+7.30\%}$
test_ppo_speed[reduce-overhead-backward] 1.0138ms 0.9622ms 1.0393 KOps/s 1.0227 KOps/s $\color{#35bf28}+1.62\%$
test_reinforce_speed[False-None] 2.2862ms 2.1474ms 465.6707 Ops/s 467.0378 Ops/s $\color{#d91a1a}-0.29\%$
test_reinforce_speed[False-backward] 3.5926ms 3.1402ms 318.4536 Ops/s 317.9386 Ops/s $\color{#35bf28}+0.16\%$
test_reinforce_speed[True-None] 0.8900ms 0.8231ms 1.2149 KOps/s 1.2091 KOps/s $\color{#35bf28}+0.48\%$
test_reinforce_speed[True-backward] 2.5205ms 2.4194ms 413.3312 Ops/s 413.7666 Ops/s $\color{#d91a1a}-0.11\%$
test_reinforce_speed[reduce-overhead-None] 22.5704ms 11.8606ms 84.3125 Ops/s 86.6168 Ops/s $\color{#d91a1a}-2.66\%$
test_reinforce_speed[reduce-overhead-backward] 1.0850ms 1.0385ms 962.9448 Ops/s 965.3750 Ops/s $\color{#d91a1a}-0.25\%$
test_iql_speed[False-None] 9.3200ms 8.8616ms 112.8468 Ops/s 113.0331 Ops/s $\color{#d91a1a}-0.16\%$
test_iql_speed[False-backward] 13.0096ms 12.5483ms 79.6918 Ops/s 79.4603 Ops/s $\color{#35bf28}+0.29\%$
test_iql_speed[True-None] 1.9025ms 1.7406ms 574.5073 Ops/s 584.9082 Ops/s $\color{#d91a1a}-1.78\%$
test_iql_speed[True-backward] 4.3932ms 4.1865ms 238.8636 Ops/s 228.5040 Ops/s $\color{#35bf28}+4.53\%$
test_iql_speed[reduce-overhead-None] 20.2549ms 11.5681ms 86.4449 Ops/s 87.4377 Ops/s $\color{#d91a1a}-1.14\%$
test_iql_speed[reduce-overhead-backward] 1.6358ms 1.5721ms 636.0784 Ops/s 641.4865 Ops/s $\color{#d91a1a}-0.84\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.8926ms 6.3189ms 158.2552 Ops/s 155.9668 Ops/s $\color{#35bf28}+1.47\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.4690ms 0.2679ms 3.7321 KOps/s 2.9158 KOps/s $\textbf{\color{#35bf28}+27.99\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6319ms 0.2637ms 3.7924 KOps/s 3.1034 KOps/s $\textbf{\color{#35bf28}+22.20\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3231ms 6.0805ms 164.4607 Ops/s 162.9846 Ops/s $\color{#35bf28}+0.91\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.1044ms 0.3233ms 3.0928 KOps/s 3.3109 KOps/s $\textbf{\color{#d91a1a}-6.59\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5277ms 0.2935ms 3.4071 KOps/s 3.9444 KOps/s $\textbf{\color{#d91a1a}-13.62\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6762ms 1.3121ms 762.1300 Ops/s 753.7505 Ops/s $\color{#35bf28}+1.11\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4278ms 1.1915ms 839.2440 Ops/s 831.5090 Ops/s $\color{#35bf28}+0.93\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4903ms 6.2745ms 159.3749 Ops/s 158.6772 Ops/s $\color{#35bf28}+0.44\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0207ms 0.4226ms 2.3663 KOps/s 2.4675 KOps/s $\color{#d91a1a}-4.10\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7312ms 0.4418ms 2.2637 KOps/s 2.5985 KOps/s $\textbf{\color{#d91a1a}-12.89\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2120ms 6.0739ms 164.6388 Ops/s 163.2883 Ops/s $\color{#35bf28}+0.83\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8506ms 0.2825ms 3.5404 KOps/s 3.2853 KOps/s $\textbf{\color{#35bf28}+7.76\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5494ms 0.2773ms 3.6059 KOps/s 3.4332 KOps/s $\textbf{\color{#35bf28}+5.03\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3569ms 6.0502ms 165.2845 Ops/s 164.7464 Ops/s $\color{#35bf28}+0.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6994ms 0.3154ms 3.1705 KOps/s 3.8081 KOps/s $\textbf{\color{#d91a1a}-16.74\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4445ms 0.2432ms 4.1118 KOps/s 3.1550 KOps/s $\textbf{\color{#35bf28}+30.33\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.7630ms 6.2796ms 159.2461 Ops/s 159.9349 Ops/s $\color{#d91a1a}-0.43\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.1118ms 0.4040ms 2.4751 KOps/s 2.1944 KOps/s $\textbf{\color{#35bf28}+12.79\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6438ms 0.4377ms 2.2847 KOps/s 2.3507 KOps/s $\color{#d91a1a}-2.80\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.9363ms 5.3315ms 187.5648 Ops/s 186.4487 Ops/s $\color{#35bf28}+0.60\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 3.9651ms 1.7444ms 573.2765 Ops/s 430.7619 Ops/s $\textbf{\color{#35bf28}+33.08\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 8.5379ms 1.2773ms 782.8973 Ops/s 784.4665 Ops/s $\color{#d91a1a}-0.20\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4820s 14.9550ms 66.8674 Ops/s 186.6294 Ops/s $\textbf{\color{#d91a1a}-64.17\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.5981ms 2.0508ms 487.6053 Ops/s 446.6915 Ops/s $\textbf{\color{#35bf28}+9.16\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.9894ms 1.2028ms 831.4219 Ops/s 858.8668 Ops/s $\color{#d91a1a}-3.20\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 7.3371ms 5.6232ms 177.8352 Ops/s 33.0513 Ops/s $\textbf{\color{#35bf28}+438.06\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 10.0676ms 2.2179ms 450.8836 Ops/s 480.8764 Ops/s $\textbf{\color{#d91a1a}-6.24\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.4749ms 1.3834ms 722.8465 Ops/s 757.5753 Ops/s $\color{#d91a1a}-4.58\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.0699ms 12.8042ms 78.0996 Ops/s 77.2201 Ops/s $\color{#35bf28}+1.14\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 22.0947ms 16.8537ms 59.3341 Ops/s 61.4848 Ops/s $\color{#d91a1a}-3.50\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 17.9682ms 17.4084ms 57.4434 Ops/s 56.5324 Ops/s $\color{#35bf28}+1.61\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 18.2030ms 16.8260ms 59.4319 Ops/s 58.3768 Ops/s $\color{#35bf28}+1.81\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 17.8064ms 17.2753ms 57.8862 Ops/s 56.8656 Ops/s $\color{#35bf28}+1.79\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.7380ms 18.4093ms 54.3204 Ops/s 56.1914 Ops/s $\color{#d91a1a}-3.33\%$

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants